{"total":102,"rows":[{"id":"2407.02490","title":"MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention","created":"2024-07-02","cited_by_count":383,"area":null},{"id":"2406.16858","title":"EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees","created":"2024-06-24","cited_by_count":370,"area":"inference"},{"id":"2503.01840","title":"EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test","created":"2025-03-03","cited_by_count":331,"area":"inference"},{"id":"2407.11550","title":"Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference","created":"2024-07-16","cited_by_count":235,"area":"inference"},{"id":"2410.21465","title":"ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference","created":"2024-10-28","cited_by_count":134,"area":"inference"},{"id":"2507.13334","title":"A Survey of Context Engineering for Large Language Models","created":"2025-07-17","cited_by_count":126,"area":null},{"id":"2410.20290","title":"Fast Best-of-N Decoding via Speculative Rejection","created":"2024-10-26","cited_by_count":112,"area":null},{"id":"2410.16179","title":"MagicPIG: LSH Sampling for Efficient LLM Generation","created":"2024-10-21","cited_by_count":111,"area":null},{"id":"2501.19324","title":"Reward-Guided Speculative Decoding for Efficient LLM Reasoning","created":"2025-01-31","cited_by_count":106,"area":"lr"},{"id":"2408.11049","title":"MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding","created":"2024-08-20","cited_by_count":91,"area":"inference"},{"id":"2405.19715","title":"SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths","created":"2024-05-30","cited_by_count":75,"area":"inference"},{"id":"2412.10319","title":"SCBench: A KV Cache-Centric Analysis of Long-Context Methods","created":"2024-12-13","cited_by_count":60,"area":"inference"},{"id":"2506.07900","title":"MiniCPM4: Ultra-Efficient LLMs on End Devices","created":"2025-06-09","cited_by_count":52,"area":null},{"id":"2405.08944","title":"Challenges in Deploying Long-Context Transformers: A Theoretical Peak Performance Analysis","created":"2024-05-14","cited_by_count":44,"area":"agents"},{"id":"2502.04420","title":"KVTuner: Sensitivity-Aware Layer-Wise Mixed-Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference","created":"2025-02-06","cited_by_count":40,"area":"inference"},{"id":"2411.00841","title":"A Theoretical Perspective for Speculative Decoding Algorithm","created":"2024-10-30","cited_by_count":29,"area":"inference"},{"id":"2502.10424","title":"QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache","created":"2025-02-05","cited_by_count":27,"area":"inference"},{"id":"2502.03805","title":"CriticalKV: Optimizing KV Cache Eviction from an Output Perturbation Perspective","created":"2025-02-06","cited_by_count":26,"area":"inference"},{"id":"2601.19278","title":"DART: Diffusion-Inspired Speculative Decoding for Fast LLM Inference","created":"2026-01-27","cited_by_count":24,"area":"inference"},{"id":"2502.19732","title":"Speculative Decoding and Beyond: An In-Depth Survey of Techniques","created":"2025-02-27","cited_by_count":23,"area":"inference"},{"id":"2408.13233","title":"Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time","created":"2024-08-23","cited_by_count":22,"area":null},{"id":"2410.05589","title":"ParallelSpec: Parallel Drafter for Efficient Speculative Decoding","created":"2024-10-08","cited_by_count":22,"area":"inference"},{"id":"2502.17421","title":"LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification","created":"2025-02-24","cited_by_count":21,"area":"agents"},{"id":"2502.14856","title":"FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling","created":"2025-02-20","cited_by_count":20,"area":"inference"},{"id":"2505.15141","title":"BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms","created":"2025-05-21","cited_by_count":20,"area":"inference"},{"id":"2404.14688","title":"FMint: Bridging Human Designed and Data Pretrained Models for Differential Equation Foundation Model","created":"2024-04-23","cited_by_count":19,"area":null},{"id":"2408.12151","title":"A Tighter Complexity Analysis of SparseGPT","created":"2024-08-22","cited_by_count":19,"area":null},{"id":"2502.18779","title":"Towards Optimal Multi-draft Speculative Decoding","created":"2025-02-26","cited_by_count":19,"area":"inference"},{"id":"2503.05096","title":"AdaSpec: Adaptive Speculative Decoding for Fast, SLO-Aware Large Language Model Serving","created":"2025-03-07","cited_by_count":18,"area":"inference"},{"id":"2502.18755","title":"M-ANT: Efficient Low-bit Group Quantization for LLMs via Mathematically Adaptive Numerical Type","created":"2025-02-26","cited_by_count":16,"area":null},{"id":"2405.09592","title":"A Survey of Generative Techniques for Spatial-Temporal Data Mining","created":"2024-05-15","cited_by_count":14,"area":null},{"id":"2502.20330","title":"RAPID: Long-Context Inference with Retrieval-Augmented Speculative Decoding","created":"2025-02-27","cited_by_count":14,"area":"rag"},{"id":"2505.19201","title":"DREAM: Drafting with Refined Target Features and Entropy-Adaptive Cross-Attention Fusion for Multimodal Speculative Decoding","created":"2025-05-25","cited_by_count":14,"area":"mllm"},{"id":"2509.04467","title":"PDTrim: Targeted Pruning for Prefill-Decode Disaggregation in Inference","created":"2025-08-29","cited_by_count":14,"area":"inference"},{"id":"2510.13334","title":"Taming the Fragility of KV Cache Eviction in LLM Inference","created":"2025-10-15","cited_by_count":14,"area":"inference"},{"id":"2509.18362","title":"FastMTP: Accelerating LLM Inference with Enhanced Multi-Token Prediction","created":"2025-09-16","cited_by_count":13,"area":"inference"},{"id":"2502.01662","title":"Fast Large Language Model Collaborative Decoding via Speculation","created":"2025-02-01","cited_by_count":12,"area":null},{"id":"2506.05333","title":"Kinetics: Rethinking Test-Time Scaling Laws","created":"2025-06-05","cited_by_count":12,"area":"lr"},{"id":"2505.24196","title":"CLaSp: In-Context Layer Skip for Self-Speculative Decoding","created":"2025-05-30","cited_by_count":11,"area":"inference"},{"id":"2408.15562","title":"Boosting Lossless Speculative Decoding via Feature Sampling and Partial Alignment Distillation","created":"2024-08-28","cited_by_count":10,"area":"inference"},{"id":"2506.04108","title":"Rectified Sparse Attention","created":"2025-06-04","cited_by_count":10,"area":"inference"},{"id":"2512.01278","title":"Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding","created":"2025-12-01","cited_by_count":10,"area":"lr"},{"id":"2503.13565","title":"ML-SpecQD: Multi-Level Speculative Decoding with Quantized Drafts","created":"2025-03-17","cited_by_count":9,"area":"inference"},{"id":"2410.20418","title":"Inevitable Trade-off between Watermark Strength and Speculative Sampling Efficiency for Language Models","created":"2024-10-27","cited_by_count":8,"area":"inference"},{"id":"2505.22135","title":"RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding","created":"2025-05-28","cited_by_count":8,"area":"inference"},{"id":"2410.10141","title":"Temperature-Centric Investigation of Speculative Decoding with Knowledge Distillation","created":"2024-10-14","cited_by_count":7,"area":"inference"},{"id":"2502.04077","title":"AttentionPredictor: Temporal Patterns Matter for KV Cache Compression","created":"2025-02-06","cited_by_count":7,"area":"inference"},{"id":"2505.12992","title":"Fractured Chain-of-Thought Reasoning","created":"2025-05-19","cited_by_count":7,"area":"lr"},{"id":"2512.02337","title":"SpecPV: Improving Self-Speculative Decoding for Long-Context Generation via Partial Verification","created":"2025-12-02","cited_by_count":7,"area":"inference"},{"id":"2602.07223","title":"Vegas: Self-Speculative Decoding with Verification-Guided Sparse Attention","created":"2026-02-06","cited_by_count":7,"area":"inference"},{"id":"2411.11055","title":"FastDraft: How to Train Your Draft","created":"2024-11-17","cited_by_count":6,"area":"inference"},{"id":"2602.01469","title":"P-EAGLE: Parallel-Drafting EAGLE with Scalable Training","created":"2026-02-01","cited_by_count":6,"area":"lr"},{"id":"2605.20104","title":"Draft Less, Retrieve More: Hybrid Tree Construction for Speculative Decoding","created":"2026-05-19","cited_by_count":6,"area":"inference"},{"id":"2405.13019","title":"A Comprehensive Survey of Accelerated Generation Techniques in Large Language Models","created":"2024-05-15","cited_by_count":5,"area":"inference"},{"id":"2406.13185","title":"LIVE: Learnable In-Context Vector for Visual Question Answering","created":"2024-06-19","cited_by_count":5,"area":null},{"id":"2505.20776","title":"SpecExtend: A Drop-in Enhancement for Speculative Decoding of Long Sequences","created":"2025-05-27","cited_by_count":5,"area":"inference"},{"id":"2506.08373","title":"Draft-based Approximate Inference for LLMs","created":"2025-06-10","cited_by_count":5,"area":"inference"},{"id":"2509.23928","title":"HiViS: Hiding Visual Tokens from the Drafter for Speculative Decoding in Vision-Language Models","created":"2025-09-28","cited_by_count":5,"area":"mllm"},{"id":"2602.20217","title":"KnapSpec: Self-Speculative Decoding via Adaptive Layer Selection as a Knapsack Problem","created":"2026-02-23","cited_by_count":5,"area":"inference"},{"id":"2604.05650","title":"See the Forest for the Trees: Loosely Speculative Decoding via Visual-Semantic Guidance for Efficient Inference of Video LLMs","created":"2026-04-07","cited_by_count":5,"area":"inference"},{"id":"2606.08446","title":"Sparrow: Sparse Rollout for Stable and Efficient Long-context RL of Large Language Models","created":"2026-06-07","cited_by_count":5,"area":"lr"},{"id":"2409.03856","title":"Sirius: Contextual Sparsity with Correction for Efficient LLMs","created":"2024-09-05","cited_by_count":4,"area":null},{"id":"2502.18890","title":"TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation","created":"2025-02-26","cited_by_count":4,"area":null},{"id":"2505.01572","title":"PipeSpec: Breaking Stage Dependencies in Hierarchical LLM Decoding","created":"2025-05-02","cited_by_count":4,"area":"inference"},{"id":"2510.02329","title":"SelfJudge: Faster Speculative Decoding via Self-Supervised Judge Verification","created":"2025-09-26","cited_by_count":4,"area":"inference"},{"id":"2510.13847","title":"DynaSpec: Context-aware Dynamic Speculative Sampling for Large-Vocabulary Language Models","created":"2025-10-11","cited_by_count":4,"area":"inference"},{"id":"2510.26843","title":"CAS-Spec: Cascade Adaptive Self-Speculative Decoding for On-the-Fly Lossless Inference Acceleration of LLMs","created":"2025-10-30","cited_by_count":4,"area":"inference"},{"id":"2602.15318","title":"Sparrow: Text-Anchored Window Attention with Visual-Semantic Glimpsing for Speculative Decoding in Video LLMs","created":"2026-02-17","cited_by_count":4,"area":"mllm"},{"id":"2602.21224","title":"Make Every Draft Count: Hidden State based Speculative Decoding","created":"2026-02-02","cited_by_count":4,"area":"inference"},{"id":"2503.00784","title":"DuoDecoding: Hardware-aware Heterogeneous Speculative Decoding with Dynamic Multi-Sequence Drafting","created":"2025-03-02","cited_by_count":3,"area":"inference"},{"id":"2505.22179","title":"Speculative Decoding Meets Quantization: Compatibility Evaluation and Hierarchical Framework Design","created":"2025-05-28","cited_by_count":3,"area":"inference"},{"id":"2506.09316","title":"On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention","created":"2025-06-11","cited_by_count":3,"area":null},{"id":"2601.08273","title":"HIPPO: Accelerating Video Large Language Models Inference via Holistic-aware Parallel Speculative Decoding","created":"2026-01-13","cited_by_count":3,"area":"inference"},{"id":"2411.05894","title":"SSSD: Simply-Scalable Speculative Decoding","created":"2024-11-08","cited_by_count":2,"area":"inference"},{"id":"2505.13254","title":"HeteroSpec: Leveraging Contextual Heterogeneity for Efficient Speculative Decoding","created":"2025-05-19","cited_by_count":2,"area":"inference"},{"id":"2506.03566","title":"POSS: Position Specialist Generates Better Draft for Speculative Decoding","created":"2025-06-04","cited_by_count":2,"area":"inference"},{"id":"2511.15898","title":"Global Resolution: Optimal Multi-Draft Speculative Sampling via Convex Minimization","created":"2025-11-19","cited_by_count":2,"area":"inference"},{"id":"2608.19758","title":"FlashPrefill V2: Block-Sparse Prefill Attention for Long-Context LLM Serving","created":"2026-08-20","cited_by_count":2,"area":"inference"},{"id":"2504.08838","title":"SD$^2$: Self-Distilled Sparse Drafters","created":"2025-04-10","cited_by_count":1,"area":"inference"},{"id":"2510.26527","title":"Polybasic Speculative Decoding Through a Theoretical Perspective","created":"2025-10-30","cited_by_count":1,"area":"inference"},{"id":"2601.20357","title":"TABED: Test-Time Adaptive Ensemble Drafting for Robust Speculative Decoding in LVLMs","created":"2026-01-28","cited_by_count":1,"area":"inference"},{"id":"2601.23180","title":"TriSpec: Ternary Speculative Decoding via Lightweight Proxy Verification","created":"2026-01-30","cited_by_count":1,"area":"inference"},{"id":"2605.01910","title":"Stochastic Sparse Attention for Memory-Bound Inference","created":"2026-05-03","cited_by_count":1,"area":"inference"},{"id":"2606.00144","title":"BudgetDraft: Acceptance-Aware Multi-View Training for Sparse-KV Speculative Decoding","created":"2026-05-29","cited_by_count":1,"area":"inference"},{"id":"2607.27735","title":"A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding","created":"2026-07-30","cited_by_count":1,"area":"inference"},{"id":"2608.26004","title":"AsymSpec: Context-Asymmetric Speculative Decoding for Agentic LLMs","created":"2026-08-26","cited_by_count":1,"area":"agents"},{"id":"2609.17943","title":"ASPIRE: Asynchronous Batched Self-Speculative Decoding for Long-Context LLM Inference","created":"2026-09-16","cited_by_count":1,"area":"inference"},{"id":"2407.00467","title":"VcLLM: Video Codecs are Secretly Tensor Codecs","created":"2024-06-29","cited_by_count":0,"area":null},{"id":"2510.19705","title":"Fast Inference via Hierarchical Speculative Decoding","created":"2025-10-22","cited_by_count":0,"area":"inference"},{"id":"2602.16961","title":"Greedy Multi-Path Block Verification for Faster Decoding in Speculative Sampling","created":"2026-02-18","cited_by_count":0,"area":"inference"},{"id":"2602.16994","title":"Dynamic Delayed Tree Expansion For Improved Multi-Path Speculative Decoding","created":"2026-02-19","cited_by_count":0,"area":"inference"},{"id":"2603.11053","title":"Speculative Decoding Scaling Laws (SDSL): Throughput Optimization Made Simple","created":"2026-02-25","cited_by_count":0,"area":"inference"},{"id":"2603.27027","title":"TAPS: Task Aware Proposal Distributions for Speculative Sampling","created":"2026-03-27","cited_by_count":0,"area":"inference"},{"id":"2605.11186","title":"CATS: Cascaded Adaptive Tree Speculation for Memory-Limited LLM Inference Acceleration","created":"2026-05-11","cited_by_count":0,"area":"inference"},{"id":"2605.28678","title":"DREAM-R: Multimodal Speculative Reasoning with RL-Based Refined Drafting, Precise Verification, and Fully Parallel Execution","created":"2026-05-27","cited_by_count":0,"area":"mllm"},{"id":"2606.24957","title":"Dustin: Draft-Augmented Sparse Verification for Efficient Long-Context Generation with Speculative Decoding","created":"2026-06-23","cited_by_count":0,"area":"inference"},{"id":"2607.24260","title":"KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems","created":"2026-07-27","cited_by_count":0,"area":"inference"},{"id":"2608.20359","title":"Self-Speculation for Faster Reasoning Models","created":"2026-06-17","cited_by_count":0,"area":"lr"},{"id":"2608.26112","title":"TreeGraft: Adaptive Multi-Drafter Grafting for Tree-Based Speculative Decoding","created":"2026-05-28","cited_by_count":0,"area":"inference"},{"id":"2608.30252","title":"Strong Drafts Need Compact Memories: Long-Context Speculative Decoding with Compressed KV Cache","created":"2026-08-31","cited_by_count":0,"area":"inference"}],"next_cursor":"100"}